Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

dont iterate streams in openai cost tracking #1138

Merged
merged 3 commits into from
May 15, 2024
Merged

Conversation

piotrm0
Copy link
Contributor

@piotrm0 piotrm0 commented May 15, 2024

Other details that are good to know but need not be announced:

  • Prevent exhausting iterables in cost-tracking code. This is responsible for some bugs. A side effect is that cost-tracking may not be working for some streaming methods for now.
  • Detect main_input and main_output by presence of "input" and "output" in dicts.

@dosubot dosubot bot added the size:L This PR changes 100-499 lines, ignoring generated files. label May 15, 2024
Copy link

Check out this pull request on  ReviewNB

See visual diffs & provide feedback on Jupyter Notebooks.


Powered by ReviewNB

@dosubot dosubot bot added the lgtm This PR has been approved by a maintainer label May 15, 2024
@joshreini1 joshreini1 merged commit 78dbb12 into main May 15, 2024
9 checks passed
piotrm0 added a commit that referenced this pull request May 29, 2024
* Remove references to running moderation endpoint on AzureOpenAI (#1116)

* azureopenai docstring

* azureopenai.md

* remove extra references to supported feedbacks

* Update azureopenai.md

* swap rag utility (qs)relevance (#1120)

* add otel semantic convention attributes

* notes

* Fix Link (#1128)

* update groundedness prompt (#1112)

Co-authored-by: Josh Reini <60949774+joshreini1@users.noreply.github.com>

* Fix docs links in instrumentation (#1129)

* fix link on langchain instrumentation docs

* fix llama-index quickstart link

* fix langchain instrumentation docs, add missing imports

* add missing imports to nemo instrumentation docs

* fix rag triad and awaitable calls (#1110)

* fix rag triad and awaitable calls

* remove locals printout in awaitables message

* add otel spec note

* extending custom tool to store the call stack for demonstration purposes, added trulens internals demonstrations notebook

* trurails: update to getattr (#1130)

* fix rag triad and awaitable calls

* remove locals printout in awaitables message

* update __getattr__ in select_context (#1119)

---------

Co-authored-by: Piotr Mardziel <piotrm@gmail.com>

* Remove placeholder feedback (#1127)

Co-authored-by: Josh Reini <60949774+joshreini1@users.noreply.github.com>

* Default names for rag triad utility (#1122)

* Update feedback.py

* use name

* add reasons to answer, context relevance; add collect to groundedness

* Update custom functions notebook to reflect context relevance change (#1134)

* Update custom_feedback_functions.ipynb

* Update README.md (#1136)

retreivers -> retrievers

* revert original spans, leave otel versions for future use

* formatting

* move temporary things into another file

* Unify groundedness interface (#1135)

* unify groundedness start

* remove groundedness.py

* groundedness nli moves

* remove custom aggregator

* groundedness aggregator to user code

* move agg to trulens side by default (groundedness)

* remove extra code

* remove hf key setting

* remove hf import

* add comment about aggregation for context relevance

* update init

* remove unneeded import

* use generate_score_and_reasons for groundedness internally

* f-strings for groundedness prompts

* docstring

* docstrings formatting

* groundedness reasons template

* remove redundant prompt

* update quickstarts

* llama-index notebooks

* rag triad helper update

* oai assistant nb

* update readme

* models notebooks updates

* iterate nbs

* mongo, pinecone nbs

* update huggingface docstring

* remove outdated docstring selector notes

* more docstring cleaning

* checkpoint tracing testing

* dont iterate streams in openai cost tracking (#1138)

* open ai streaming adjustments in cost tracking

* notes

* delete outputs

* Automated File Generation from Docs Notebook Changes (#1137)

Co-authored-by: joshreini1 <joshreini1@users.noreply.github.com>
Co-authored-by: Josh Reini <60949774+joshreini1@users.noreply.github.com>

* Fix a few old groundedness references (#1139)

* Update selecting_components.md

* Update MultiQueryRetrievalLangchain.ipynb

* Update random_evaluation.ipynb

* Update canopy_quickstart.ipynb

* Update all_tools.py

* Update llama_index_quickstart.ipynb

* Automated File Generation from Docs Notebook Changes (#1141)

Co-authored-by: joshreini1 <joshreini1@users.noreply.github.com>

* rename and docs of temp file

* add freeze/thaw for exporters/importers

* update comprehensiveness + nb (#1064)

* update comprehensiveness + nb

* nb expansion

* fix typo

* meetingbank transcript data

* oss models in app

* test

* benchmarking gpt-3.5-turbo, gpt-4-turbo, and gpt-4o

* update path

* comprehensiveness benchmark

* updated summarization_eval nb

* fix normalization

* show improvement in comprehensiveness feedback functions

---------

Co-authored-by: Daniel <dah0417912@gmail.com>

* complexifying the example custom app

* debugging

* context nesting testing

* 0.29.0 version bump (#1140)

* version bump

* simpler lc quickstart

* update installs and imports

* update langchain instrumentation docs

* remove groundedness ref from providers.md

* build docs fixes

* remove key cell

* fix docs build

* firx formatting for stock.md

* remove extra spaces

* undo format change

* update docstrings for hugs and base provider

* openai docstring updates

* hugs docstring update

* update context relevance hugs docstring

* more docstring updates

* remove can be changed messages from openai provider docstrings

* Automated File Generation from Docs Notebook Changes (#1143)

Co-authored-by: joshreini1 <joshreini1@users.noreply.github.com>

* glossary additions (#1144)

* add to glossary

* finish some terms

* clean up notebook

* split off contexts examples

* move more things into context examples

* fixing some instrumentation stuff to be more robust

* prototyping json queries

* Update ollama_quickstart.ipynb

* don't remember

* add deprecation message for old module attributes

* adjust notes

* Patch imports error (#1146)

* add httpx to requirements

* undo httpx add

* test add langchain-community

* change langchain-community required version

* add langchain_community to optional imports and checks for use of openai endpoint (#1154)

* first

* adjust docs

* logic

* add langhain_community to pinecone reqs too

* adjust trubot example with new reqs

* more reqs

* remove extra text

* add langchain_community to a few imports in notebooks

---------

Co-authored-by: Piotr Mardziel <piotrm@Piotrs-Laptop.local>
Co-authored-by: Josh Reini <60949774+joshreini1@users.noreply.github.com>

* 0.30.0 bump (#1158)

Co-authored-by: Josh Reini <joshua.reini@snowflake.com>

* 0.30.1 bump (#1159)

Co-authored-by: Josh Reini <joshua.reini@snowflake.com>

* update ref to groundedness fn (#1161)

---------

Co-authored-by: Josh Reini <60949774+joshreini1@users.noreply.github.com>
Co-authored-by: Tim Baumgärtner <baumgaertner.t@gmail.com>
Co-authored-by: Brian McGough <bpmcgough@gmail.com>
Co-authored-by: Aaron <163380706+arn-tru@users.noreply.github.com>
Co-authored-by: Josh Reini <joshreini1@gmail.com>
Co-authored-by: Ikko Eltociear Ashimine <eltociear@gmail.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: joshreini1 <joshreini1@users.noreply.github.com>
Co-authored-by: Daniel <dah0417912@gmail.com>
Co-authored-by: Piotr Mardziel <piotrm@Piotrs-Laptop.local>
Co-authored-by: Josh Reini <joshua.reini@snowflake.com>
sfc-gh-dhuang pushed a commit that referenced this pull request Jun 28, 2024
* open ai streaming adjustments in cost tracking

* notes

* delete outputs
sfc-gh-dhuang pushed a commit that referenced this pull request Jul 1, 2024
* open ai streaming adjustments in cost tracking

* notes

* delete outputs
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
lgtm This PR has been approved by a maintainer size:L This PR changes 100-499 lines, ignoring generated files.
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants